mksglu/context-mode

10 INSANE GITHUB REPOS THAT REDUCE CLAUDE CODE TOKENS BY UP TO 90% 1. RTK (Rust Token Killer) Filters terminal output before feeding it into context. Can reduce by 60-90% with commonly used dev commands. github.com/rtk-ai/rtk 2. Context Mode Offloads Playwright or GitHub tool outputs to SQLite, passing only clean summaries to the conversation. 98% reduction. github.com/mksglu/context-mo… 3. code-review-graph Uses Tree-sitter to build a local knowledge graph of the codebase. Claude only reads the necessary parts, achieving 49x reduction for large monorepos. github.com/tirth8205/code-re… 4. Token Savior An MCP server that references code by symbols instead of entire files. 97% reduction with code navigation, zero external dependencies. github.com/Mibayy/token-savi… 5. Caveman Claude Makes Claude speak in caveman-style tone to cut output tokens by 65-75%. Maintains technical accuracy. github.com/JuliusBrussee/cav… 6. claude-token-efficient Just place a CLAUDE.md file to keep outputs concise. No code changes needed, ideal for verbose sessions. github.com/drona23/claude-to… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool control. Compresses repeated tool outputs for 95%+ reduction. github.com/ooples/token-opti… 8. claude-token-optimizer Reusable setup prompt collection to optimize projects. Save 90% of tokens in just 5 minutes. github.com/nadimtuhin/claude… 9. token-optimizer Discovers ghost tokens that silently devour context. No quality degradation even after compaction. github.com/alexgreensh/token… 10. claude-context (by Zilliz) MCP that brings the entire codebase into context with BM25 + vector search. ~40% reduction with equivalent search accuracy. github.com/zilliztech/claude… Save this for later🔖

Matched through a repo-specific project phrase query.

Stop paying for Claude Max. Before you upgrade your plan to get more context, install this first. Context Mode is a free MCP server that makes your existing context window last 6x longer by never letting raw tool output touch it in the first place. → A full Playwright snapshot: 56 KB → 299 bytes → 20 GitHub issues: 59 KB → 1.1 KB → 500-request access log: 45 KB → 155 bytes → 986 KB repo research via subagent: 62 KB final context → 7.5 MB JSON API response with 20,000 records: 0.9 KB The reason you keep hitting your context limit isn't the model. It's that every MCP tool dumps raw data into the conversation. Fix the plumbing, stop buying bigger tanks. github.com/mksglu/context-mo… 8.5K stars. ELv2 License. 100% Opensource.

Matched through a repo-specific project phrase query.

Özellikle token limitleriyle boğuşan geliştiriciler için context-mode gerçekten hayat kurtarıcı... 10 güne yakındır kullanıyorum ve inanılmaz verim aldım. Gerçekten başarılı ve en önemlisi limitler konusunda beni inanılmaz rahatlattı. Mert'in de yazdığı gibi AI ile çalışırken asıl mesai kodu anlamaya gidiyor ve context-mode bu süreci çok iyi yönetiyor. Lokal SQLite tabanlı olması gizlilik açısından harika olmuş. Ellerine sağlık @mksglu 👏🏻

Matched through a repo-specific project phrase query.

THESE 10 GITHUB REPOS CUT CLAUDE CODE TOKEN COSTS BY 90% 1. RTK (Rust Token Killer) Filters terminal output before feeding it into context. Can reduce by 60-90% with commonly used dev commands. github.com/rtk-ai/rtk 2. Context Mode Offloads Playwright or GitHub tool outputs to SQLite, passing only clean summaries to the conversation. 98% reduction. github.com/mksglu/context-mo… 3. code-review-graph Uses Tree-sitter to build a local knowledge graph of the codebase. Claude only reads the necessary parts, achieving 49x reduction for large monorepos. github.com/tirth8205/code-re… 4. Token Savior An MCP server that references code by symbols instead of entire files. 97% reduction with code navigation, zero external dependencies. github.com/Mibayy/token-savi… 5. Caveman Claude Makes Claude speak in caveman-style tone to cut output tokens by 65-75%. Maintains technical accuracy. github.com/JuliusBrussee/cav… 6. claude-token-efficient Just place a CLAUDE.md file to keep outputs concise. No code changes needed, ideal for verbose sessions. github.com/drona23/claude-to… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool control. Compresses repeated tool outputs for 95%+ reduction. github.com/ooples/token-opti… 8. claude-token-optimizer Reusable setup prompt collection to optimize projects. Save 90% of tokens in just 5 minutes. github.com/nadimtuhin/claude… 9. token-optimizer Discovers ghost tokens that silently devour context. No quality degradation even after compaction. github.com/alexgreensh/token… 10. claude-context (by Zilliz) MCP that brings the entire codebase into context with BM25 + vector search. ~40% reduction with equivalent search accuracy. github.com/zilliztech/claude… Save this for later🔖

Matched through a repo-specific project phrase query.

10 GitHub Repos That Cut Claude Code Token Usage by Up to 90% 1. RTK (Rust Token Killer) Filters terminal output before it enters the context. Saves 60–90% tokens on common dev commands. 👉 github.com/rtk-ai/rtk 2. Context Mode Offloads Playwright and GitHub tool outputs into SQLite, passing only clean summaries into conversations. Up to 98% reduction. 👉 github.com/mksglu/context-mo… 3. code-review-graph Uses Tree-sitter to build a local knowledge graph of your codebase. Claude only reads what’s needed — up to 49× reduction on large monorepos. 👉 github.com/tirth8205/code-re… 4. Token Savior An MCP server that references code at the symbol level instead of entire files. Achieves ~97% reduction with zero external dependencies. 👉 github.com/Mibayy/token-savi… 5. Caveman Claude Forces Claude to respond in caveman-style language, reducing output tokens by 65–75% while keeping technical accuracy intact. 👉 github.com/JuliusBrussee/cav… 6. claude-token-efficient Just drop a CLAUDE.md file into your project to keep outputs concise. No code changes needed — great for verbose sessions. 👉 github.com/drona23/claude-to… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool control. Compresses repeated tool outputs for 95%+ savings. 👉 github.com/ooples/token-opti… 8. claude-token-optimizer Reusable setup prompts to optimize your entire project. Takes 5 minutes to implement, saves up to 90% tokens. 👉 github.com/nadimtuhin/claude… 9. token-optimizer Detects “ghost tokens” silently consuming context. Maintains quality even after aggressive compaction. 👉 github.com/alexgreensh/token… 10. claude-context (by Zilliz) MCP using BM25 + vector search to index your full codebase. ~40% token reduction with high retrieval accuracy. 👉 github.com/zilliztech/claude… Save this — once you start using even 2–3 of these together, your token usage drops dramatically without hurting output quality.

Matched through a repo-specific project phrase query.

$GSD 2 .. Another Day .. Another Ship 2.77 landed today with Context Mode — a dispatch behavior that builds task-ready context automatically: it pulls in the most relevant project artifacts, prior session state, milestone/slice signals, and execution metadata before the model runs. This reduces manual prompt assembly, improves continuity across turns, and helps tasks start with the right files and constraints from the first dispatch. github.com/gsd-build/gsd-2

Matched through a repo-specific project phrase query.

10 GitHub Repos That Cut Claude Code Token Usage by Up to 90% 1. RTK (Rust Token Killer) Filters terminal output before it enters the context. Saves 60–90% tokens on common dev commands. 👉 github.com/rtk-ai/rtk 2. Context Mode Offloads Playwright and GitHub tool outputs into SQLite, passing only clean summaries into conversations. Up to 98% reduction. 👉 github.com/mksglu/context-mo… 3. code-review-graph Uses Tree-sitter to build a local knowledge graph of your codebase. Claude only reads what’s needed — up to 49× reduction on large monorepos. 👉 github.com/tirth8205/code-re… 4. Token Savior An MCP server that references code at the symbol level instead of entire files. Achieves ~97% reduction with zero external dependencies. 👉 github.com/Mibayy/token-savi… 5. Caveman Claude Forces Claude to respond in caveman-style language, reducing output tokens by 65–75% while keeping technical accuracy intact. 👉 github.com/JuliusBrussee/cav… 6. claude-token-efficient Just drop a CLAUDE.md file into your project to keep outputs concise. No code changes needed — great for verbose sessions. 👉 github.com/drona23/claude-to… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool control. Compresses repeated tool outputs for 95%+ savings. 👉 github.com/ooples/token-opti… 8. claude-token-optimizer Reusable setup prompts to optimize your entire project. Takes 5 minutes to implement, saves up to 90% tokens. 👉 github.com/nadimtuhin/claude… 9. token-optimizer Detects “ghost tokens” silently consuming context. Maintains quality even after aggressive compaction. 👉 github.com/alexgreensh/token… 10. claude-context (by Zilliz) MCP using BM25 + vector search to index your full codebase. ~40% token reduction with high retrieval accuracy. 👉 github.com/zilliztech/claude… Save this — once you start using even 2–3 of these together, your token usage drops dramatically without hurting output quality.

Matched through a repo-specific project phrase query.

Hey folks! Context Mode founder is here. Thank you for sharing that. If you'd any question for that just DM me or feel free to create GitHub issues or PRs. We're welcoming always new members and building amazing community! LFG.

Matched through a repo-specific project phrase query.

10 github repos to cut your claude code tokens by 60-90%. rtk, context mode, code-review-graph, token savior, caveman, token-optimizer-mcp, claude-context, and more. all verified, all free. plus which 2-3 to actually stack. aiia.ro/blog/claude-code-tok…

Matched through a repo-specific project phrase query.